Qwen
Qwen3 235B A22B
Qwen3 235B A22B is an open-weights 235B-parameter model by Qwen. It is listed as in-progress on the local.ai leaderboard.
MoEopen weights
Parameters
235B
MoE · 22B active parameters
Benchmarks (local.ai snapshot)
HuggingFace metadata · updated 2025-07-26
Metadata refreshed from the HuggingFace API (snapshot 2026-08-15T15:53:42.405Z). Context length and long-form descriptions are the next pipeline stage.
Does it fit your hardware?
Detect or select your GPU first. Green = weights + context headroom, yellow = tight, grey = does not fit.
Q4_K_M 136.3GQ6_K 211.5GQ8_0 258.5GFP16 470G| Quantization | ≈ File size | Note |
|---|---|---|
| IQ2_XXS | 63.5 GB | Extreme compression, largest quality loss |
| IQ3_XXS | 84.6 GB | Very small |
| Q3_K_M | 108.1 GB | Small |
| NVFP4 | 117.5 GB | NVIDIA 4-bit |
| Q4_K_S | 126.9 GB | Common |
| Q4_K_M | 136.3 GB | Most common sweet spot |
| Q5_K_M | 178.6 GB | Balanced |
| Q6_K | 211.5 GB | Near-lossless |
| Q8_0 | 258.5 GB | Near-lossless |
| FP16 | 470 GB | Original weights |
Actual files on HuggingFace
| File | Size |
|---|---|
| model-00030-of-00118.safetensors | 3.72 GB |
| model-00111-of-00118.safetensors | 3.72 GB |
| model-00029-of-00118.safetensors | 3.72 GB |
| model-00110-of-00118.safetensors | 3.72 GB |
| model-00034-of-00118.safetensors | 3.72 GB |
| model-00039-of-00118.safetensors | 3.72 GB |
GGUF: unsloth/Qwen3-235B-A22B-GGUF · 145,802 downloads
| File | Size | |
|---|---|---|
| BF16/Qwen3-235B-A22B-BF16-00001-of-00010.gguf | 46.15 GB | download |
| BF16/Qwen3-235B-A22B-BF16-00002-of-00010.gguf | 46.21 GB | download |
| BF16/Qwen3-235B-A22B-BF16-00003-of-00010.gguf | 46.35 GB | download |
| BF16/Qwen3-235B-A22B-BF16-00004-of-00010.gguf | 46.35 GB | download |
| BF16/Qwen3-235B-A22B-BF16-00005-of-00010.gguf | 46.35 GB | download |
| BF16/Qwen3-235B-A22B-BF16-00006-of-00010.gguf | 46.35 GB | download |
| BF16/Qwen3-235B-A22B-BF16-00007-of-00010.gguf | 46.35 GB | download |
| BF16/Qwen3-235B-A22B-BF16-00008-of-00010.gguf | 46.35 GB | download |
| BF16/Qwen3-235B-A22B-BF16-00009-of-00010.gguf | 46.35 GB | download |
| BF16/Qwen3-235B-A22B-BF16-00010-of-00010.gguf | 21.20 GB | download |
| IQ4_XS/Qwen3-235B-A22B-IQ4_XS-00001-of-00003.gguf | 46.55 GB | download |
| IQ4_XS/Qwen3-235B-A22B-IQ4_XS-00002-of-00003.gguf | 46.46 GB | download |
GGUF: unsloth/Qwen3-VL-235B-A22B-Instruct-GGUF · 14,087 downloads
| File | Size | |
|---|---|---|
| BF16/Qwen3-VL-235B-A22B-Instruct-BF16-00001-of-00010.gguf | 46.15 GB | download |
| BF16/Qwen3-VL-235B-A22B-Instruct-BF16-00002-of-00010.gguf | 46.21 GB | download |
| BF16/Qwen3-VL-235B-A22B-Instruct-BF16-00003-of-00010.gguf | 46.35 GB | download |
| BF16/Qwen3-VL-235B-A22B-Instruct-BF16-00004-of-00010.gguf | 46.35 GB | download |
| BF16/Qwen3-VL-235B-A22B-Instruct-BF16-00005-of-00010.gguf | 46.35 GB | download |
| BF16/Qwen3-VL-235B-A22B-Instruct-BF16-00006-of-00010.gguf | 46.35 GB | download |
| BF16/Qwen3-VL-235B-A22B-Instruct-BF16-00007-of-00010.gguf | 46.35 GB | download |
| BF16/Qwen3-VL-235B-A22B-Instruct-BF16-00008-of-00010.gguf | 46.35 GB | download |
| BF16/Qwen3-VL-235B-A22B-Instruct-BF16-00009-of-00010.gguf | 46.35 GB | download |
| BF16/Qwen3-VL-235B-A22B-Instruct-BF16-00010-of-00010.gguf | 21.20 GB | download |
| IQ4_NL/Qwen3-VL-235B-A22B-Instruct-IQ4_NL-00001-of-00003.gguf | 46.53 GB | download |
| IQ4_NL/Qwen3-VL-235B-A22B-Instruct-IQ4_NL-00002-of-00003.gguf | 46.53 GB | download |
What you save self-hosting this model
Uses the model's own API price when it exists; otherwise the closest commercial equivalent.
Waiting for hardware detection…
RunLocal presents third-party leaderboard data (local.ai / Exo Labs, 2026-08) with its own fit and cost estimates. Verify pricing, licenses and file sizes at the source before deploying a model.